Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1805 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.4547. Min Act: -0.0000

Data Index: 144944 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.5796. Min Act: -0.0000

Data Index: 286695 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3171. Min Act: -0.0000

Data Index: 818149 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3272. Min Act: -0.0000

Data Index: 1179582 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2237. Min Act: -0.0000

Data Index: 393922 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.1969. Min Act: -0.0000

Data Index: 721629 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3057. Min Act: -0.0000

Data Index: 940124 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.1282. Min Act: -0.0000

Data Index: 684739 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.8969. Min Act: -0.0000

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.8402. Min Act: -0.0000

Data Index: 850476 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.6775. Min Act: -0.0000

Data Index: 545820 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.0888. Min Act: -0.0000

Data Index: 1359665 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.9098. Min Act: -0.0000

Data Index: 131381 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.7576. Min Act: -0.0000

Data Index: 191023 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.6588. Min Act: -0.0000

Data Index: 660370 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.6298. Min Act: -0.0000

Data Index: 1117423 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.9336. Min Act: -0.0000

Data Index: 1224080 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.7501. Min Act: -0.0000

Data Index: 418738 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.8090. Min Act: -0.0000

Data Index: 1125366 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.5753. Min Act: -0.0000

Data Index: 103170 (C4 (Web Text))

Max Activating Token Index: 622